Search Results (61)

This study evaluates the performance and scalability of fluoride-salt-lubricated hydrodynamic journal bearings used in primary pumps for Fluoride-salt-cooled High-temperature Reactors (FHRs). Because full-scale pump prototypes have not been tested, a scaling analysis is used to relate laboratory results to commercial conditions. Bearings with different length-to-diameter (L/D) ratios were assessed over a range of shaft speeds to quantify geometric and hydrodynamic effects. High-temperature bushing test data in FLiBe at 650 °C were used as inputs to three-dimensional computational fluid dynamics (CFD) simulations in STAR-CCM+. Applied load, friction force, and power loss were computed across operating speeds. Applied load increases linearly with shaft speed due to hydrodynamic pressure buildup, while power loss increases approximately quadratically, indicating greater energy dissipation at higher speeds. The resulting correlations clarify scaling effects beyond small-scale testing and provide a basis for bearing design optimization, prototype development, and the deployment of FHR technology. This work benchmarks speed-scaling relations for fluoride-salt-lubricated hydrodynamic journal bearings within the investigated regime. Full article

Underwater image enhancement remains challenging due to wavelength-dependent absorption, spatially varying scattering, and non-uniform illumination, which jointly cause severe color distortion, contrast degradation, and structural information loss. To address these issues, we propose UCS-Net, a degradation-aware dual-path framework that exploits the complementarity between global and local representations. A spatial color balance module first stabilizes the chromatic distribution of degraded inputs through a learnable gray-world-guided normalization, mitigating wavelength-induced color bias prior to feature extraction. The network then adopts a dual-branch architecture, where a hierarchical Swin Transformer branch models long-range contextual dependencies and global color relationships, while a multi-scale residual convolutional branch focuses on recovering local textures and structural details suppressed by scattering. Furthermore, a multi-scale attention fusion mechanism adaptively integrates features from both branches in a degradation-aware manner, enabling dynamic emphasis on global or local cues according to regional attenuation severity. A hue-preserving reconstruction module is finally employed to suppress color artifacts and ensure faithful color rendition. Extensive experiments on UIEB, EUVP, and UFO benchmarks demonstrate that UCS-Net consistently outperforms state-of-the-art methods in both full-reference and non-reference evaluations. Qualitative results further confirm its effectiveness in restoring fine structural details while maintaining globally consistent and visually realistic colors across diverse underwater scenes. Full article

In this study, a multi-objective optimization framework based on an artificial neural network (ANN) was developed for an inlet perforated distributor plate in a 24S24P 10 kWh cylindrical lithium-ion battery module using immersion cooling. A combined Newman, Tiedeman, Gu and Kim with Computational Fluid Dynamics (NTGK-CFD) model was used to generate a symmetrically designed space by varying the input variables, including hole size A (mm), hole spacing ΔH (mm), and coolant mass flow rate V_in (kg/s). A three-level full factorial design was used to generate 27 cases, then CFD simulations were performed to provide a training data for the ANN model to predict the output variables, including maximum temperature T_max, maximum temperature difference ΔT_max, and pressure drop ΔP. The results show that the ANN model provides a reliable predictive model, capable of reproducing the thermal-hydraulic behavior of the immersion-cooled battery module with high fidelity via correlation coefficients R of 0.997 for all three output variables. In addition, Pareto-based optimization shows designs that balance cooling efficiency and pumping power. The selected optimal solution maintains T_max within the optimal range at 37.97 °C while reducing ΔP by up to 44%, providing a practical solution for large-scale battery module thermal management in EVs. Full article

Low-light image enhancement (LLIE) requires modeling spatially extensive and interdependent degradations across large pixel regions, while directly equipping diffusion-based LLIE with heavy global modules inside the iterative denoising backbone leads to prohibitive computational overhead. To enhance long-range context modeling without inflating the per-step cost of diffusion, we propose ECA-Diff, a diffusion framework augmented with a deep External Context-Aware Encoder (ECAE). A latent-space context network built with hybrid Transformer–Convolution blocks extracts holistic cues from the input, generates multi-scale context features once, and injects them into the diffusion backbone as lightweight conditional guidance across all sampling steps. In addition, a CIELAB-space Luminance-Adaptive Chromaticity Loss regularizes conditional diffusion training and mitigates the cool color cast frequently observed in low-luminance regions. Experiments on paired and unpaired benchmarks show that ECA-Diff consistently outperforms recent state-of-the-art LLIE methods in both full-reference (PSNR/SSIM/LPIPS) and no-reference (NIQE/BRISQUE) metrics, with the external context path introducing only modest overhead relative to the baseline diffusion backbone. These results indicate that decoupling global context estimation from the iterative denoising process is an effective way to boost diffusion-based LLIE and provides a general compute-once conditioning paradigm for low-level image restoration. Full article

Accurate segmentation of medical images is essential for clinical diagnosis and treatment planning. Hyperspectral imaging (HSI), with its rich spectral information, enables improved tissue characterization and structural localization compared with traditional grayscale or RGB imaging. However, the effective modeling of both spatial and spectral dependencies remains a significant challenge, particularly in small-scale medical datasets. In this study, we propose GSA-Net, a 3D segmentation framework that integrates Gated Spectral-Axial Attention (GSA) to capture long-range interband dependencies and enhance spectral feature discrimination. The GSA module incorporates multilayer perceptrons (MLPs) and adaptive LayerScale mechanisms to enable the fine-grained modulation of spectral attention across feature channels. We evaluated GSA-Net on a hyperspectral cholangiocarcinoma (CCA) dataset, achieving an average Intersection over Union (IoU) of 60.64 ± 14.48%, Dice coefficient of 74.44 ± 11.83%, and Hausdorff Distance of 76.82 ± 42.77 px. It outperformed state-of-the-art baselines. Further spectral analysis revealed that informative spectral bands are widely distributed rather than concentrated, and full-spectrum input consistently outperforms aggressive band selection, underscoring the importance of adaptive spectral attention for robust hyperspectral medical image segmentation. Full article

This study has compiled the first impact-crater dataset for Mercury with diameters greater than 400 m by a multimodal deep-learning pipeline. We present an enhanced deep learning framework for large-scale planetary crater detection, extending the YOLOLens architecture through the integration of multimodal inputs: optical imagery, digital terrain models (DTMs), and hillshade derivatives. By incorporating morphometric data, the model achieves robust detection of impact craters that are often imperceptible in optical imagery alone, especially in regions affected by low contrast, degraded rims, or shadow-dominated illumination. The resulting catalogs LU6M371TGT for the Moon and ME6M300TGT for Mercury constitute the most comprehensive automated crater inventories to date, demonstrating the effectiveness of multimodal learning and cross-planet transfer. This work highlights the critical role of terrain information in planetary object detection and establishes a scalable, high-throughput pipeline for planetary surface analysis using modern deep learning tools. To validate the pipeline, we compare its predictions against the manually annotated catalogs for the Moon, Mercury, and several regional inventories, observing close agreement across the full diameter spectrum, revealing a high level of confidence in our approach. This work presents a spatial density analysis, comparing the spatial density maps of small and large craters highlighting the uneven distribution of crater sizes across Mercury. We explore the prevalence of kilometer-scale (1–5 km range) impact craters, demonstrating that these dominate the crater population in certain regions of Mercury’s surface. Full article

Reliable multiscale models of thrombosis require platelet-scale fidelity at organ-scale cost, a gap that scientific machine learning has the potential to narrow. We trained a DeepONet surrogate on platelet dynamics generated with LAMMPS for platelets spanning ten elastic moduli and capillary numbers (0.07–0.77). The network takes as input the wall shear stress, bond stiffness, time, and initial particle coordinates and returns the full three-dimensional deformation of the membrane. Mean-squared-error minimization with Adam and adaptive learning-rate decay yields a median displacement error below 1%, a 90th percentile below 3%, and a worst case below 4% over the entire calibrated range while accelerating computation by four to five orders of magnitude. Leave-extremes-out retraining shows acceptable extrapolation: the held-out stiffest and most compliant platelets retain sub-3% median error and an 8% maximum. Error peaks coincide with transient membrane self-contact, suggesting improvements via graph neural trunks and physics-informed torque regularization. These results represent a first demonstration of how the surrogate has the potential for coupling with continuum CFD, enabling future platelet-resolved hemodynamic simulations in patient-specific geometries and opening new avenues for predictive thrombosis modeling. Full article

Base Mine Lake (BML) is the first full-scale demonstration of water-capped tailing technology in a pit lake to reclaim lands impacted by surface mining in the Alberta Oil Sands Region (AOSR). Biogeochemical cycling and/or exchange near the fluid water interface (FWI) of the organic-rich fluid fine tailings (FFT) can hinder the reclamation process. To monitor this activity, sedimentary depth profiles were collected from three platforms (P1 to P3) at BML. Seventy-four chromatographically well-resolved petroleum hydrocarbon (PHC) isomers were quantified at each depth interval using comprehensive two-dimensional gas chromatography time-of-flight mass spectrometry (GC × GC/TOFMS). The range of total concentrations of all isomers examined across the FFT was the highest at P1 (range = 3.6 × 10⁰–5.5 × 10³ ng/g TOC), second highest at P2 (range = 3.8 × 10⁰–1.9 × 10³ ng/g TOC), and lowest at P3 (range = 5.6 × 10⁰–7.1 × 10² ng/g TOC). The elevated levels of the same isomers across platforms suggest a consistent source fingerprint. While the source fingerprint was mostly consistent across the platforms and depths, Principal Component Analysis (PCA) identified small differences between geospatial locations caused by variations in specific isomer concentrations. Hierarchical Clustering Analysis (HCA) identified the isomers responsible for the PCA separation, showing that the concentrations of low-molecular-weight n-alkanes (C11–C13) and drimane varied compared to the heavier PHCs with depth. These alkanes are the most biodegradable of the compounds identified in this study, and their variations may reflect biogeochemical cycling within the FFT. Combining these statistical tools provided deeper insight into how isomer concentrations vary with depth, helping to identify possible influences like changing inputs, biogeochemical cycling, and species exchange with the water column. Full article

Hydraulic excavators operate in harsh environments where direct measurement of actuator chamber pressures and boom displacement is often unreliable or infeasible. This study presents a novel control strategy that estimates actuator chamber pressures from work port pressures using differential equations, eliminating the need for direct pressure or position sensors. A fuzzy logic-based proportional–derivative (PD) controller is developed to mitigate boom oscillations, particularly under high-inertia load conditions and variable operator inputs. The controller dynamically adjusts gains through fuzzy logic-based gain scheduling, enhancing adaptability across a wide range of operating conditions. The proposed method addresses the limitations of classical PID controllers, which struggle with the nonlinearities, parameter uncertainties, and instability introduced by counterbalance valves and pressure-compensated proportional valves. Experimental data is used to design fuzzy rules and membership functions, ensuring robust performance. Simulation and full-scale experimental validation demonstrate that the fuzzy PD controller significantly reduces pressure overshoot (by 23% during extension and 32% during retraction) and decreases settling time (by 31.23% and 28%, respectively) compared to conventional systems. Frequency-domain stability analysis confirms exponential stability and improved damping characteristics. The proposed control scheme enhances system reliability and safety, making it ideal for excavators operating in remote or rugged terrains where conventional sensor-based systems may fail. This approach is generalizable and does not require modifications to the existing hydraulic circuit, offering a practical and scalable solution for modern hydraulic machinery. Full article

This editorial introduces the Special Issue entitled “Phase Change Materials for Building Energy Applications”, which gathers nine original research articles focused on advancing thermal energy storage solutions in the built environment. The selected contributions explore the application of phase change materials (PCMs) across a range of building components and systems, including façades, flooring, glazing, and pavements, aimed at enhancing energy efficiency, reducing peak loads, and improving thermal comfort. This Special Issue highlights both experimental and numerical investigations, ranging from nanomaterial-enhanced PCMs and solid–solid PCM glazing systems to full-scale applications and the modeling of encapsulated PCM geometries. Collectively, these studies reflect the growing potential of PCMs to support sustainable, low-carbon construction and provide new insights into material design, system optimization, and energy resilience. We thank all contributing authors and reviewers for their valuable input and hope that this Special Issue serves as a resource for ongoing innovation in the field. Full article

Trees play a critical role in climate regulation, biodiversity, and carbon storage as they cover approximately 30% of the global land area. Nowadays, Machine Learning (ML)is key to automating large-scale tree species classification based on active and passive sensing systems, with a recent trend favoring data fusion approaches for higher accuracy. The use of 3D Deep Learning (DL) models has improved tree species classification by capturing structural and geometric data directly from point clouds. We propose a fully Multimodal Tree Species Classification Network (MMTSCNet) that processes Light Detection and Ranging (LiDAR) point clouds, Full-Waveform (FWF) data, derived features, and bidirectional, color-coded depth images in their native data formats without any modality transformation. We conduct several experiments as well as an ablation study to assess the impact of data fusion. Classification performance on the combination of Airborne Laser Scanning (ALS) data with FWF data scored the highest, achieving an Overall Accuracy (OA) of nearly 97%, a Mean Average F1-score (MAF) of nearly 97%, and a Kappa Coefficient of 0.96. Results for the other data subsets show that the ALS data in combination with or even without FWF data produced the best results, which was closely followed by the UAV-borne Laser Scanning (ULS) data. Additionally, it is evident that the inclusion of FWF data provided significant benefits to the classification performance, resulting in an increase in the MAF of +4.66% for the ALS data, +4.69% for the ULS data under leaf-on conditions, and +2.59% for the ULS data under leaf-off conditions. The proposed model is also compared to a state-of-the-art unimodal 3D-DL model (PointNet++) as well as a feature-based unimodal DL architecture (DSTCN). The MMTSCNet architecture outperformed the other models by several percentage points, depending on the characteristics of the input data. Full article

Background: Epigenetic biomarkers, particularly CpG methylation, are increasingly employed in clinical and forensic settings. However, we still lack a cost-effective, sensitive, medium-scale method for the analysis of hundreds to thousands of user-defined CpGs suitable for minute DNA input amounts (<10 ng). In this study, motivated by promising results in the genetics field, we investigated single-molecule molecular inversion probes (smMIPs) for simultaneous analysis of hundreds of CpGs by using an example set of 514 age-associated CpGs (Zhang model). Methods: First, we developed a novel smMIP design tool to suit bisulfite-converted DNA (Locksmith). Then, to optimize the capture process, we performed single-probe capture for ten selected, representative smMIPs. Based on this pilot, the full smMIP panel was tested under varying capture conditions, including hybridization and elongation temperature, smMIP and template DNA amounts, dNTP concentration and elongation time. Results: Overall, we found that the capture efficiency was highly probe-(and hence, sequence-) dependent, with a heterogeneous coverage distribution across CpGs higher than the 1000-fold range. Considering CpGs with at least 20X coverage, we yielded robust methylation detection with levels comparable to those obtained from the gold standard EPIC microarray analysis (Pearsons’s r: 0.96). Conclusions: The observed low specificity and uniformity indicate that smMIPs in their current form are not compatible with the lowered complexity of bisulfite-converted DNA. Full article

We present an automatic approach for generating learning problems for teaching introductory programming in different programming languages. The current implementation allows input and output in the three most popular programming languages for teaching introductory programming courses: C++, Java, and Python. The generator stores learning problems using the “meaning tree”, a language-independent representation of a syntax tree. During this study, we generated a bank of 1,428,899 learning problems focused on the order of expression evaluation. They were generated in about 16 h. The learning problems were classified for further use with the used concepts, possible domain-rule violations, and required skills; they covered a wide range of difficulties and topics. The problems were validated by automatically solving them in an intelligent tutoring system that recorded the actual skills used and violations made. The generated problems were favorably assessed by 10 experts: teachers and teaching assistants in introductory programming courses. They noted that the problems are ready for use without further manual improvement and that the classification system is flexible enough to receive problems with desirable properties. The proposed approach combines the advantages of different state-of-the-art methods. It combines the diversity of learning problems generated by restricted randomization and large language models with full correctness and a natural look of template-based problems, which makes it a good fit for large-scale learning problem generation. Full article

The need for energy efficiency in neighborhood-scale architectural design is driven by environmental imperatives and escalating energy costs. This study identifies three key phases in a design process framework where machine learning can be applied to optimize energy consumption in early design stages. The overall framework integrates machine learning tools into the design workflow, enhancing design exploration from concept level and enabling targeted energy assessments. This paper focuses on the first phase (Phase 1) of the framework, which employs machine learning for building energy forecasting using only the few inputs available in a business-as-usual early-stage design workflow. The CatBoost model was selected for its high accuracy in predicting energy consumption using minimal input data. A preliminary application to a case study in New York City showed high predictive accuracy while reducing the input needed, with R² scores of 0.88 for both cross-validation and test datasets. Shapely additive explanation analysis validated the selection of key influencing parameters such as building area, principal building activity, and climate zones. The test demonstrated discrepancies between the test data-driven model and a physics-based energy model values ranging from −8.69% to 11.04%, which can be considered an acceptable result in early-stage design. The remaining two phases, though outside the scope of this study, are introduced at a conceptual level to provide an overview of the full framework. Phase 2 will analyze building shape and elevation, assessing the total energy use intensity, while Phase 3 will apply district-level energy optimization across interconnected buildings. The findings from Phase 1 underscore the potential of machine learning to integrate energy efficiency considerations into neighborhood-scale design from the earliest stages, providing reliable predictions that can inform sustainable design. Full article

This study examines the three-axis vibration isolation capabilities of a full-scale magnetorheological (MR) seat suspension system utilizing experimental methods to assess performance under both single-axis and simultaneous three-axis input conditions. To achieve this, a semi-active MR seat damper was designed and manufactured to address excitations in all three axes. The damper effectiveness was tested experimentally for axial and lateral motions, focusing on dynamic stiffness and loss factor using an MTS machine. Prior to creating the full-scale MR seat suspension, a scaled-down version at one-third size was developed to verify the damper’s ability to effectively reduce vibrations in response to practical excitation levels. Additionally, a narrow-band frequency-shaped semi-active control (NFSSC) algorithm was developed to optimize vibration suppression. Ultimately, a full-scale MR seat suspension was assembled and tested with a 50th percentile male dummy, and comprehensive three-axis vibration isolation tests were conducted on a hydraulic multi-axis simulation table (MAST) for both individual inputs over a frequency range up to 200 Hz and for simultaneous multi-directional inputs. The experimental results demonstrated the effectiveness of the full-scale MR seat suspension in reducing seat vibrations. Full article